Can an algorithm detect signs of a serious eye disease in premature infants like human experts?

May 02, 2018

Bottom Line: An algorithm could detect signs of a serious eye disease in images from premature infants with accuracy comparable to or better than human experts.

Why The Research Is Interesting: Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide. The decision to treat is primarily based on the presence of plus disease, which is when retinal vessels are dilated and twisted. However, clinical diagnosis of plus disease can be highly subjective and variable.

What and When: A machine learning algorithm was trained to diagnose plus disease using 5,511 retinal photographs. Data were collected from July 2011 to December 2016 and analyzed from December 2016 to September 2017.

Study Measures: The algorithm to detect plus disease was tested on an independent set of 100 images against eight ROP experts.

Authors: Michael F. Chiang, M.D., Oregon Health and Science University, Portland, Jayashree Kalpathy-Cramer, Ph.D., Massachusetts General Hospital, Boston, and coauthors

Results: The algorithm diagnosed plus disease with comparable or better accuracy than human ROP experts.

Study Limitations: Algorithms in artificial neural networks are only as good as the data on which they are trained. It is unknown how factors such as image quality, resolution, different camera systems and field of view may affect the output of these deep learning systems.
For more details and to read the full study, please visit the For The Media website.


Editor's Note: Please see the article for additional information, including other authors, author contributions and affiliations, financial disclosures, funding and support, etc.

Want to embed a link to this study in your story? Link will be live at the embargo time

JAMA Ophthalmology

Related Algorithm Articles from Brightsurf:

CCNY & partners in quantum algorithm breakthrough
Researchers led by City College of New York physicist Pouyan Ghaemi report the development of a quantum algorithm with the potential to study a class of many-electron quantums system using quantum computers.

Machine learning algorithm could provide Soldiers feedback
A new machine learning algorithm, developed with Army funding, can isolate patterns in brain signals that relate to a specific behavior and then decode it, potentially providing Soldiers with behavioral-based feedback.

New algorithm predicts likelihood of acute kidney injury
In a recent study, a new algorithm outperformed the standard method for predicting which hospitalized patients will develop acute kidney injury.

New algorithm could unleash the power of quantum computers
A new algorithm that fast forwards simulations could bring greater use ability to current and near-term quantum computers, opening the way for applications to run past strict time limits that hamper many quantum calculations.

QUT algorithm could quash Twitter abuse of women
Online abuse targeting women, including threats of harm or sexual violence, has proliferated across all social media platforms but QUT researchers have developed a sophisticated statistical model to identify misogynistic content and help drum it out of the Twittersphere.

New learning algorithm should significantly expand the possible applications of AI
The e-prop learning method developed at Graz University of Technology forms the basis for drastically more energy-efficient hardware implementations of Artificial Intelligence.

Algorithm predicts risk for PTSD after traumatic injury
With high precision, a new algorithm predicts which patients treated for traumatic injuries in the emergency department will later develop posttraumatic stress disorder.

New algorithm uses artificial intelligence to help manage type 1 diabetes
Researchers and physicians at Oregon Health & Science University have designed a method to help people with type 1 diabetes better manage their glucose levels.

A new algorithm predicts the difficulty in fighting fire
The tool completes previous studies with new variables and could improve the ability to respond to forest fires.

New algorithm predicts optimal materials among all possible compounds
Skoltech researchers have offered a solution to the problem of searching for materials with required properties among all possible combinations of chemical elements.

Read More: Algorithm News and Algorithm Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to